Cited 0 times in Scipus Cited Count

Time Series AI Model for Acute Kidney Injury Detection Based on a Multicenter Distributed Research Network: Development and Verification Study

DC Field Value Language
dc.contributor.authorHeo, S-
dc.contributor.authorKang, EA-
dc.contributor.authorYu, JY-
dc.contributor.authorKim, HR-
dc.contributor.authorLee, S-
dc.contributor.authorKim, K-
dc.contributor.authorHwangbo, Y-
dc.contributor.authorPark, RW-
dc.contributor.authorShin, H-
dc.contributor.authorRyu, K-
dc.contributor.authorKim, C-
dc.contributor.authorJung, H-
dc.contributor.authorChegal, Y-
dc.contributor.authorLee, JH-
dc.contributor.authorPark, YR-
dc.date.accessioned2024-09-27T00:19:54Z-
dc.date.available2024-09-27T00:19:54Z-
dc.date.issued2024-
dc.identifier.urihttp://repository.ajou.ac.kr/handle/201003/32827-
dc.description.abstractBackground: Acute kidney injury (AKI) is a marker of clinical deterioration and renal toxicity. While there are many studies offering prediction models for the early detection of AKI, those predicting AKI occurrence using distributed research network (DRN)–based time series data are rare. Objective: In this study, we aimed to detect the early occurrence of AKI by applying an interpretable long short-term memory (LSTM)–based model to hospital electronic health record (EHR)–based time series data in patients who took nephrotoxic drugs using a DRN. Methods: We conducted a multi-institutional retrospective cohort study of data from 6 hospitals using a DRN. For each institution, a patient-based data set was constructed using 5 drugs for AKI, and an interpretable multivariable LSTM (IMV-LSTM) model was used for training. This study used propensity score matching to mitigate differences in demographics and clinical characteristics. Additionally, the temporal attention values of the AKI prediction model’s contribution variables were demonstrated for each institution and drug, with differences in highly important feature distributions between the case and control data confirmed using 1-way ANOVA. Results: This study analyzed 8643 and 31,012 patients with and without AKI, respectively, across 6 hospitals. When analyzing the distribution of AKI onset, vancomycin showed an earlier onset (median 12, IQR 5-25 days), and acyclovir was the slowest compared to the other drugs (median 23, IQR 10-41 days). Our temporal deep learning model for AKI prediction performed well for most drugs. Acyclovir had the highest average area under the receiver operating characteristic curve score per drug (0.94), followed by acetaminophen (0.93), vancomycin (0.92), naproxen (0.90), and celecoxib (0.89). Based on the temporal attention values of the variables in the AKI prediction model, verified lymphocytes and calcvancomycin ium had the highest attention, whereas lymphocytes, albumin, and hemoglobin tended to decrease over time, and urine pH and prothrombin time tended to increase. Conclusions: Early surveillance of AKI outbreaks can be achieved by applying an IMV-LSTM based on time series data through an EHR-based DRN. This approach can help identify risk factors and enable early detection of adverse drug reactions when prescribing drugs that cause renal toxicity before AKI occurs.-
dc.language.isoen-
dc.titleTime Series AI Model for Acute Kidney Injury Detection Based on a Multicenter Distributed Research Network: Development and Verification Study-
dc.typeArticle-
dc.identifier.pmid39039992-
dc.identifier.urlhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC11263760-
dc.subject.keywordadverse drug reaction-
dc.subject.keywordadverse reaction-
dc.subject.keywordadverse reactions-
dc.subject.keywordartificial intelligence-
dc.subject.keywordcommon data model-
dc.subject.keyworddetect-
dc.subject.keyworddetection-
dc.subject.keyworddistributed research network-
dc.subject.keywordkidney-
dc.subject.keywordmachine learning-
dc.subject.keywordmulticenter study-
dc.subject.keywordnephrology-
dc.subject.keywordpharmaceutical-
dc.subject.keywordpharmaceutics-
dc.subject.keywordpharmacology-
dc.subject.keywordpharmacy-
dc.subject.keywordreal world data-
dc.subject.keywordrenal-
dc.subject.keywordtime series-
dc.subject.keywordtime series AI-
dc.subject.keywordtoxic-
dc.subject.keywordtoxicity-
dc.contributor.affiliatedAuthorPark, RW-
dc.type.localJournal Papers-
dc.identifier.doi10.2196/47693-
dc.citation.titleJMIR medical informatics-
dc.citation.volume12-
dc.citation.date2024-
dc.citation.startPagee47693-
dc.citation.endPagee47693-
dc.identifier.bibliographicCitationJMIR medical informatics, 12. : e47693-e47693, 2024-
dc.identifier.eissn2291-9694-
dc.relation.journalidJ022919694-
Appears in Collections:
Journal Papers > School of Medicine / Graduate School of Medicine > Biomedical Informatics
Files in This Item:
39039992.pdfDownload

qrcode

해당 아이템을 이메일로 공유하기 원하시면 인증을 거치시기 바랍니다.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse